How to Use Claude Fable 5.2 in Muse
Claude Fable 5.2 is built for difficult coding, deep research, and extended technical tasks. Compared with Claude Fable 5.1, Anthropic reports improvements in coding, reasoning, and vision.
Prompts to try with Claude Fable 5.2 in Muse
Copy an example into Muse, or ask in your own words.
Use Claude Fable 5.2 to compare a queue-based design with a synchronous design for processing customer exports. Exports can take ten minutes, must survive worker restarts, and must not run twice. Recommend an approach in under 700 words, with assumptions and failure cases.
Use Claude Fable 5.2 to analyze the research excerpts in this conversation. Identify where the findings agree, where they conflict, and which conclusions the evidence supports. Produce a 600-word brief with references to the supplied excerpts.
Use Claude Fable 5.2 with high reasoning effort to examine the incident timeline in this conversation. Separate observations from hypotheses, rank plausible causes, and propose tests that could distinguish them. Do not present an untested cause as established.
Use Claude Fable 5.2 to turn the technical notes in this conversation into a decision memo. Include the problem, constraints, options, recommendation, and unresolved questions. Keep it under 800 words and use only the evidence supplied.
Use Claude Fable 5.2 to challenge the engineering proposal in this conversation. Find unsupported assumptions, conflicting requirements, and missing acceptance criteria. Return the five most consequential issues and one concrete question for each.
How to set up Claude Fable 5.2 in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Claude Fable 5.2
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "anthropic", "model": "anthropic/claude-fable-5.2", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse finds Claude Fable 5.2 on Spiral, shows the price and runs it.
Claude Fable 5.2 providers and prices
Spiral runs Claude Fable 5.2 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.21372 per run at the default inputs. $10.40 per 1M input tokens, $0.26 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $52.00 per 1M output tokens.
Settings you can ask for
Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Max tokens | 1 to 128000 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Reasoning effort | low, medium, high, xhigh, or max | high | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Fable 5.2 is on its tool page: open its card above.
What can you do with Claude Fable 5.2 in Muse?
Work through difficult technical decisions and turn supplied evidence into a finished explanation with Claude Fable 5.2. State the decision, constraints, and desired answer length so the conversation produces something you can use.
Diagnose a difficult software bug
Ask Claude Fable 5.2 to trace a failure through the relevant code, identify a reproducible cause, and propose a focused fix with verification.
Plan a complex code change
Have Claude Fable 5.2 map dependencies, identify behavior that must stay consistent, and develop an implementation plan with acceptance checks.
Compare technical approaches
Give Claude Fable 5.2 competing designs and explicit requirements. Request a recommendation that identifies assumptions, tradeoffs, and unanswered questions.
Synthesize technical research
Provide source excerpts and ask Claude Fable 5.2 to reconcile competing findings, distinguish evidence from inference, and identify the next questions to investigate.
Turn analysis into a technical report
Ask Claude Fable 5.2 to develop supplied findings into a finished report with recommendations, supporting evidence, and clearly stated gaps.
Review a multistep technical investigation
Have Claude Fable 5.2 assess completed experiments, identify unresolved hypotheses, and produce a prioritized plan for the remaining investigation.
More on Claude Fable 5.2 and Muse
Overview
Claude Fable 5.2 in other agents
Questions about Claude Fable 5.2 in Muse
Can Muse use Claude Fable 5.2?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Claude Fable 5.2 like any built-in tool.
How much does Claude Fable 5.2 cost in Muse?
Up to $0.21372 per run at the default inputs. $10.40 per 1M input tokens, $0.26 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $52.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need an Anthropic account to use Claude Fable 5.2 in Muse?
You need no Anthropic account. Muse uses one Spiral API key for every tool, and Spiral runs Claude Fable 5.2 on its own Anthropic account.
How long does it take to set up Claude Fable 5.2 in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while Claude Fable 5.2 runs?
Claude Fable 5.2 runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Fable 5.2 best suited for?
Use it for difficult coding, multistep research, and technical analysis that needs a finished deliverable. Give it a concrete result to produce and clear criteria for completion.
How much context and output can Claude Fable 5.2 handle?
It supports a one-million-token context window and up to 128,000 output tokens. These are token limits, so avoid treating them as fixed page or word counts.
Which reasoning effort should I use?
Start with high effort and compare results on representative tasks. Increase effort for difficult work only when testing shows a benefit; lower it when the results still meet your requirements.
Can I turn Claude Fable 5.2 thinking off?
Adaptive thinking is always enabled. Adjust effort to control thinking depth, and request a specific answer length separately.
What should I do if Claude Fable 5.2 stops before finishing?
State the remaining deliverable and tell it to continue through ordinary, recoverable obstacles. Early stopping is more common at lower effort levels, so test high effort for extended tasks.
Start using Claude Fable 5.2 in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


